This paper presents a new probability table memory compression method based on mixture models and its application to N-tuple recognizers and N-gram character language models. Joint probability tables are decomposed into lower dimensional probability components and their mixtures. The maximum likelihood parameters of the mixture models are trained by the expectation maximization (EM) algorithm and quantized to one byte integers. Probability elements that mixture models do not estimate reliably are kept separately. Experimental results with on-line handwritten UNIPEN uppercase and lowercase characters show that the total memory size of an on-line scanning N-tuple recognizer is reduced from 12.3 MB to 0.66 MB bytes, while the recognition rate drops from 91.64% to 91.13% for uppercase characters and from 88.44% to 87.31% for lowercase characters. The N-gram character language model was compressed from 73.6 MB to 0.58 MB with minimal reduction in performance.


    Access

    Check access

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    Probability table compression for handwritten character recognition


    Contributors:
    Sung-Jung Cho, (author) / Perrone, M. (author) / Ratzlaff, E. (author)


    Publication date :

    2003-01-01


    Size :

    2070536 byte




    Type of media :

    Conference paper


    Type of material :

    Electronic Resource


    Language :

    English



    Probability Table Compression for Handwritten Character Recognition

    Cho, S. / Perrone, M. / Ratzlaff, G. et al. | British Library Conference Proceedings | 2003


    Fuzzy Logic in Handwritten Character Recognition

    Kiselev, V. V. | British Library Online Contents | 2003



    Handwritten Hangul Character Recognition with Hierarchical Stochastic Character Representation

    Kang, K. / Kim, J. / Institute of Electrical and Electronics Engineers | British Library Conference Proceedings | 2003


    Using Normal Patterns in Handwritten Character Recognition

    Tascini, G. / Montesanto, A. / Puliti, P. et al. | British Library Conference Proceedings | 1999